ai-social-media-content

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation guides and additional tools hosted on the developer's official GitHub repository and infrastructure.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined natural language prompts to generate content via external AI models.
  • Ingestion points: Social media content prompts passed as arguments to CLI commands in SKILL.md.
  • Boundary markers: Input prompts are encapsulated within JSON strings.
  • Capability inventory: The skill utilizes the Bash tool, restricted to the specific vendor CLI command.
  • Sanitization: The instructions do not define specific sanitization or filtering for the natural language content provided to the generation models.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 10:23 AM
Security Audit — agent-trust-hub — ai-social-media-content